Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    sign-offs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Decoration
    -0.07
    irector
    -0.07
    lista
    -0.06
    Transactions
    -0.06
     telephone
    -0.06
    foon
    -0.06
    Certificates
    -0.06
    _FC
    -0.06
    "}↵↵
    -0.06
    iyorum
    -0.06
    POSITIVE LOGITS
    genden
    0.07
     eager
    0.07
     різні
    0.07
     zájem
    0.06
    错
    0.06
     обов
    0.06
     留
    0.06
     Chamber
    0.06
     jspb
    0.06
     coerce
    0.06
    Act Density 0.213%

    No Known Activations